© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101544
    Prev
    Next
    INDEX
    Explanations

    specific items or instructions

    np_acts-logits-general · gemini-2.5-flash-lite

    sometimes trigger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ה
    0.49
    I
    0.48
    ре
    0.47
    ophylline
    0.47
    С
    0.46
    rocess
    0.46
     принять
    0.46
    잇
    0.46
     décou
    0.45
    то
    0.44
    POSITIVE LOGITS
    麻煩
    0.47
    बाइक
    0.43
     कमलेश
    0.41
    دو
    0.39
    怛
    0.39
     조건
    0.39
     २०
    0.39
    䉍
    0.38
     organizational
    0.38
     vésicules
    0.38
    Activations Density 0.000%

    No Known Activations